logo AAUBS Data Science 2022
  • Info, Schedule & Co
    • Infrastructure
    • Modules
    • Literature & Resources
    • Semester Schedule
    • Semester Project Requirements
  • 1. Applied Data Science and Machine Learning
    • Basics of Statistical Programming and Data Manipulation (W35-36)
      • Basics Statistical Programming
      • Statistics Refresher
      • Basics Data Visualization
      • Hands-on data manipulation and EDA
      • EDA workshop & Working with JSON/APIs/MongoDB
      • M1 EDA Hackathon
      • Rapid Prototyping with Streamlit
      • Mathematics (Brushup)
    • Intro to Unsupervised Machine Learning (W38)
      • Unsupervised Machine Learning (UML) intro
      • UML Appliations - Recommender Systems
    • Supervised Machine Learning (W39)
      • Supervised Machine Learning (SML)
      • Time Series Forecasts
      • SML - Further topics
      • SML Appliations - Airbnb Pricing
  • 2. Network Analysis & NLP
    • Network Analysis
      • Basics Network Analysis
      • 2 Mode Networks
      • NW Exercises
      • NW Cases
    • Natural Language Processing
      • Basics of NLP
      • NLP - Other areas
      • NLP Applications Chatbot
      • NLP Word Vectors
  • 4. Applied Deep Learning and Artificial Intelligence
    • Intro to Deep Learning
      • Basics Deep Learning
      • Neural network architectures
      • Exercise Session 1
      • Group assignment 1
    • Neural network architectures
      • CNNs
      • RNNs and LSTMs
      • Exercise Session 2
      • Group assignment 2
    • Intro to transformer models
      • Introduction to transformers
      • Sentence-Transformers SBERT
      • Exercise Session 3
      • Group assignment 3
    • Transformer models in 2023
      • Fine-tuning transformers
      • Timeseries Transformers intro
      • Exercise Session 4
  • 5. Data Governance and Ethics
    • In-calss Presentations
  • 6. Data Engineering and MLOps
    • Databases
      • Introduction to databases
      • Building PoC with DB backend
      • Portfolio Assignment Databases
    • MLOps: A Framework and Maturity Model
    • Big Data workflows
      • Introduction to Big Data workflows
      • Exercise 2: Performing a Big Data workflow with Spark and Polars
      • Group assignment 2
    • From notebook to API
      • From notebook to API
    • MLOps
      • Introduction MLOps with mlflow
      • MLOps on AWS: a Hands-On Tutorial
      • Group assignment 3
    • Deployment
      • From notebook to containarized app in the cloud
      • Introduction to Docker and deploying scalable ML
      • Group assignment 4

  • Clear History

Built with from Grav and Hugo

Social / Business Data Science 2022 > Applied Deep Learning and Artificial Intelligence > Intro to transformer models > Introduction to transformers

Introduction to transformers

Literature

Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.

The illustrated transformer

Simple transformer LM

Notebooks

  • Seq2Seq - Neural Machine Translation

  • Simple transformer LM

Slides